{"id":"https://openalex.org/W1530495682","doi":null,"title":"Scalable Techniques for Clustering the Web (Extended Abstract)","display_name":"Scalable Techniques for Clustering the Web (Extended Abstract)","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W1530495682","mag":"1530495682"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.170.3330","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.3330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rakaposhi.eas.asu.edu/cse494/notes/haveli-cluster.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045119735","display_name":"Taher H. Haveliwala","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taher H. Haveliwala","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022164041","display_name":"Aristides Gionis","orcid":"https://orcid.org/0000-0002-5211-112X","observed_orcids":["https://orcid.org/0000-0002-5211-112X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aristides Gionis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076056716","display_name":"Piotr Indyk","orcid":"https://orcid.org/0009-0005-2022-8429","observed_orcids":["https://orcid.org/0009-0005-2022-8429"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr Indyk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6338,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88004518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.7099999785423279,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.7099999785423279,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.10830000042915344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.030400000512599945,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/web-document-clustering","display_name":"web page clustering","score":0.9509999752044678},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"locality-sensitive hashing","score":0.9470000267028809},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.699999988079071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7708443403244019},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7455243468284607},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.6741043329238892},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6509298086166382},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5985583066940308},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5727409720420837},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5125967860221863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43075430393218994},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3748883605003357},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2612072229385376},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.24655213952064514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13374093174934387},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.170.3330","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.170.3330","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rakaposhi.eas.asu.edu/cse494/notes/haveli-cluster.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.43.2294","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.2294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/conf/webdb2000/PAPERS/8c.ps","raw_type":"text"},{"id":"mag:1530495682","doi":null,"is_oa":false,"landing_page_url":"http://dbpubs.stanford.edu:8090/pub/2000-23","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W3627347","https://openalex.org/W1502916507","https://openalex.org/W1956559956","https://openalex.org/W2003262311","https://openalex.org/W2073583237","https://openalex.org/W2081193615","https://openalex.org/W2098162425","https://openalex.org/W2100958137","https://openalex.org/W2130610812","https://openalex.org/W2132069633","https://openalex.org/W2140129471","https://openalex.org/W2147717514","https://openalex.org/W2152565070","https://openalex.org/W2167044614"],"related_works":["https://openalex.org/W192724328","https://openalex.org/W2980396724","https://openalex.org/W2790518931","https://openalex.org/W7098485351","https://openalex.org/W138738517","https://openalex.org/W4308907428","https://openalex.org/W2055886766","https://openalex.org/W1984958534","https://openalex.org/W4226190468","https://openalex.org/W2754607325"],"abstract_inverted_index":{"Clustering":[0,20],"is":[1],"one":[2],"of":[3,14,28,37,55,77,100],"the":[4,11,18,35,50,53,86,92],"most":[5],"crucial":[6],"techniques":[7],"for":[8],"dealing":[9],"with":[10],"massive":[12],"amount":[13],"information":[15],"present":[16],"on":[17,34,49,85],"web.":[19],"can":[21,95],"either":[22],"be":[23,96],"performed":[24,32],"once":[25],"offline,":[26],"independent":[27],"search":[29,38],"queries,":[30],"or":[31],"online":[33],"results":[36],"queries.":[39],"Our":[40,82],"offline":[41],"approach":[42],"aims":[43],"to":[44,98],"efficiently":[45],"cluster":[46],"similar":[47,70],"pages":[48,62,71],"web,":[51],"using":[52],"technique":[54],"Locality-Sensitive":[56],"Hashing":[57],"(LSH),":[58],"in":[59,65],"which":[60],"web":[61],"are":[63],"hashed":[64],"such":[66],"a":[67,73],"way":[68],"that":[69,91],"have":[72,89],"much":[74],"higher":[75],"probability":[76],"collision":[78],"than":[79],"dissimilar":[80],"pages.":[81],"preliminary":[83],"experiments":[84],"Stanford":[87],"WebBase":[88],"shown":[90],"hash-based":[93],"scheme":[94],"scaled":[97],"millions":[99],"urls.":[101]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}